TempCompass — leaderboard
Temporal reasoning benchmark for video LLMs testing understanding of temporal dynamics, ordering, and duration in videos.
Metric: Avg All (%). Source: huggingface.co. Status: saturated. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 73.8 |
| 2 | Qwen 2 VL 7B Instruct | 67.8 |
| 3 | Gemini 1.5 Pro | 67.1 |
| 4 | MiniCPM-V-2.6 | 66.3 |
| 5 | InternVL2-8B | 66 |
Interactive version: theaggregate.ai/benchmark?slug=tempcompass · How the rankings work · Data refreshed daily, snapshot 2026-07-22.